China

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in VLMs compensates for possibly weak visual features by contextualizing or enriching them. Using three CLIP-based VLMs, we perform controlled self-attention ablations on a carefully designed probing task. Our findings show that despite known limitations, CLIP visual representations offer ready-to-read semantic information to the language decoder. However, in scenarios of reduced contextualization in the visual representations, the language decoder can largely compensate for the deficiency and recover performance. This suggests a dynamic division of labor in VLMs and motivates future architectures that offload more visual processing to the language decoder.

EMNLP 2025

LLMs Can Compensate for Deficiencies in Visual Representations

attention knockout

representation analysis

vision-language models

multimodal representation

contextualization

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Annotated datasets for supervised learning tasks often contain incorrect gold annotations, i.e. label noise. To address this issue, many noisy label learning approaches incorporate metrics to filter out unreliable samples, for example using heuristics such as high loss or low confidence. However, when these metrics are integrated into larger pipelines, it becomes difficult to compare their effectiveness, and understand their individual contribution to reducing label noise. This paper directly compares popular sample metrics for detecting incorrect annotations in named entity recognition (NER). NER is commonly approached as token classification, so the metrics are calculated for each training token and we flag the incorrect ones by defining metrics thresholds. We compare the metrics based on (i) their accuracy in detecting the incorrect labels and (ii) the test scores when retraining a model using the cleaned dataset. We show that training dynamics metrics work the best overall. The best metrics effectively reduce the label noise across different noise types. The errors that the model has not yet memorized are more feasible to detect, and relabeling these tokens is a more effective strategy than excluding them from training.

Token-Level Metrics for Detecting Incorrect Gold Annotations in Named Entity Recognition

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to users’ emotional needs. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose a novel two-stage framework that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality preference dataset with turn-level strategy-response pairs. Then training on ESC-Pro with Chain-of-Strategy Optimization (CSO) improves both strategy accuracy and bias mitigation, enabling LLMs to generate more empathetic and contextually appropriate responses. Experiments on LLaMA-3.1-8B, Gemma-2-9B, and Qwen2.5-7B demonstrate that CSO outperforms standard SFT, highlighting the efficacy of fine-grained, turn-level preference modeling in ESC.

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter

The frequency distribution of words in human-written texts roughly follows a simple mathematical form known as Zipf's law. Somewhat less well known is the related Heaps' law, which describes a sublinear power-law growth of vocabulary size with document size. We study the applicability of Zipf's and Heaps' laws to texts generated by Large Language Models (LLMs). We empirically show that Heaps’ and Zipf's laws only hold for LLM-generated texts in a narrow model-dependent temperature range. These temperatures have an optimal value close to t=1 for all the base models except the large Llama models, are higher for instruction-finetuned models and do not depend on the model size or prompting. This independently confirms the recent discovery of phase transitions in LLM-generated texts.

Zipf’s and Heaps’ Laws for Tokens and LLM-generated Texts

Understanding and solving complex reasoning tasks is vital for addressing the information needs of a user. Although dense neural models learn contextualised embeddings, they still underperform on queries containing negation. To understand this phenomenon, we study negation in both traditional neural information retrieval and LLM-based models. We (1) introduce a taxonomy of negation that derives from philosophical, linguistic, and logical definitions; (2) generate two benchmark datasets that can be used to evaluate the performance of neural information retrieval models and to fine-tune models for a more robust performance on negation; and (3) propose a logic-based classification mechanism that can be used to analyze the performance of retrieval models on existing datasets. Our taxonomy produces a balanced data distribution over negation types, providing a better training setup that leads to faster convergence on the NevIR dataset. Moreover, we propose a classification schema that reveals the coverage of negation types in existing datasets, offering insights into the factors that might affect the generalisation of fine-tuned models on negation.

A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers

Language models built from various sources are the foundation of today’s NLP progress. However, for many low-resource languages, the diversity of domains is often limited, more biased to a religious domain, which impacts their performance when evaluated on distant and rapidly evolving domains such as social media. Domain adaptive pre-training (DAPT) and task-adaptive pre-training (TAPT) are popular techniques to reduce this bias through continual pre-training for BERT-based models, but they have not been explored for African multilingual gual encoders. In this paper, we explore DAPT and TAPT continual pertaining approaches for the African languages social media domain. We introduce AfriSocial - a large-scale social media and news domain corpus for continual pre-training on several African languages. Leveraging AfriSocial, we show that DAPT consistently improves performance on three subjective tasks: sentiment analysis, multi-label emotion, and hate speech classification, covering 19 languages from 1% to 30% F1 score. Similarly, leveraging TAPT on one task data improves performance on other related tasks. For example, training with unlabeled sentiment data (source) for a fine-grained emotion classification task (target) improves the baseline results by an F1 score ranging from 0.55% to 15.11%. Combining these two methods (i.e. DAPT + TAPT) further improves the overall performance.

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text

As Large Language Models (LLMs) gain expertise across diverse domains and modalities, scalable oversight becomes increasingly challenging, particularly when their capabilities may surpass human evaluators. Debate has emerged as a promising mechanism for enabling such oversight. In this work, we extend the debate paradigm to a multimodal setting, exploring its potential for weaker models to supervise and enhance the performance of stronger models. We focus on visual question answering (VQA), where two "sighted" expert vision-language models debate an answer, while a "blind" (text-only) judge adjudicates based solely on the quality of the arguments. In our framework, the experts defend only answers aligned with their beliefs, thereby obviating the need for explicit role-playing and concentrating the debate on instances of expert disagreement. Experiments on several multimodal tasks demonstrate that the debate framework consistently outperforms individual expert models. Moreover, judgments from weaker LLMs can help instill reasoning capabilities in vision-language models through finetuning.

Debating for Better Reasoning in Vision-Language Models

Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations—text that is inconsistent with visual input, due to the limited ability to verify information in different regions of the image. To address this, we propose **Multi-Region Fusion Decoding (MRFD)**, a training-free decoding method that improves factual grounding by modeling inter-region consistency. MRFD identifies salient regions using cross-attention, generates initial responses for each, and computes reliability weights based on Jensen-Shannon Divergence (JSD) among the responses. These weights guide a consistency-aware fusion of per-region predictions, using region-aware prompts inspired by Chain-of-Thought reasoning. Experiments across multiple LVLMs and benchmarks show that MRFD significantly reduces hallucinations and improves response factuality without requiring model updates.

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs

LLMs have been widely adopted to tackle many traditional NLP tasks. Their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language. In this work, we examine LLMs' generalization in under-resourced settings through the task of orthographic normalization across Otomi language variants. We develop two approaches: a rule-based method using a finite-state transducer (FST) and an in-context learning (ICL) method that provides the model with string transduction examples. We compare the performance of FSTs and neural approaches in low-resource scenarios, providing insights into their potential and limitations. Our results show that while FSTs outperform LLMs in zero-shot settings, ICL enables LLMs to surpass FSTs, stressing the importance of combining linguistic expertise with machine learning in current approaches for low-resource scenarios

FSTs vs ICL: Generalisation in LLMs for an under-resourced language

Existing tool-learning methods usually rely on supervised fine-tuning, they often overlook fine-grained optimization of internal tool call details, leading to limitations in preference alignment and error discrimination. To overcome these challenges, we propose **T**oken-level **T**ool-use **P**reference **A**lignment Training Framework (TTPA), a training paradigm for constructing token-level tool-use preference datasets that align LLMs with fine-grained preferences using a novel error-oriented scoring mechanism. TTPA first introduces reversed dataset construction, a method for creating high-quality, multi-turn tool-use datasets by reversing the generation flow. Additionally, we propose **T**oken-level **P**reference **S**ampling (TPS) to capture fine-grained preferences by modeling token-level differences during generation. To address biases in scoring, we introduce the **E**rror-oriented **S**coring **M**echanism (ESM), which quantifies tool-call errors and can be used as a training signal. Extensive experiments on three diverse benchmark datasets demonstrate that TTPA significantly improves tool-using performance while showing strong generalization ability across models and datasets.

TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation

We present SMARTMiner, a framework for extracting and evaluating SMART (Specific, Measurable, Attainable, Relevant, Time-bound) goals from unstructured health coaching (HC) notes. Developed in response to challenges observed during a clinical trial, the SMARTMiner achieves two tasks: (i) extracting behavior-change goal spans, and (ii) categorizing their SMARTness. We introduce SMARTSpan, the first publicly available dataset of 173 HC notes annotated with 266 goals and SMART attributes. SMARTMiner incorporates an extractive goal retriever with a component-wise SMART classifier. Experiment results show that extractive models significantly outperformed their generative counterparts in low-resource settings, and that two-stage fine-tuning substantially boosted performance. The classifier achieved up to 0.91 SMART F1 score, while the full SMARTMiner maintained high end-to-end accuracy. This work bridges healthcare, behavioral science, and natural language processing to support health coaches and clients with structured goal tracking--paving way for automated weekly goal reviews between human-led HC sessions. Code and the dataset will be released upon acceptance.

Downloads

Next from EMNLP 2025

Token-Level Metrics for Detecting Incorrect Gold Annotations in Named Entity Recognition

Similar lecture

Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models